Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/pruthvinathjv/nextjs-claude-code-kit/check-boundariesgit clone --depth 1 https://github.com/pruthvinathJV/nextjs-claude-code-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/pruthvinathjv/nextjs-claude-code-kit/check-boundaries)<a href="https://agentmods.dev/commands/pruthvinathjv/nextjs-claude-code-kit/check-boundaries"><img src="https://agentmods.dev/badge/commands/pruthvinathjv/nextjs-claude-code-kit/check-boundaries.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00482 |
| Opus 5 | $0.00000 | $0.00241 |
| Sonnet 5 | $0.00000 | $0.00096 |
| Haiku 4.5 | $0.00000 | $0.00048 |
Grade A, and why
check-boundaries scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Review the component tree in $ARGUMENTS for incorrect or unnecessary 'use client' directives.
For each component file found:
-
Check if 'use client' is present
-
If yes, verify it is actually required by checking whether the component uses:
- Browser APIs (window, document, localStorage, sessionStorage)
- Event handlers that require client state (onClick with useState, onChange with controlled inputs)
- React hooks that depend on client state: useState, useEffect, useReducer, useRef for DOM manipulation
- Client-only third-party libraries
-
Flag as INCORRECTLY CLIENTED if 'use client' is present but the component:
- Only renders JSX with no interactivity
- Only passes props down to child components
- Does data fetching that could be done in a Server Component
- Has 'use client' because a child needed it (the child should have it, not the parent)
-
For each incorrectly cliented component, suggest the fix:
- If the component itself needs no client features: remove 'use client', make it a Server Component
- If only a small part needs client features: identify which piece to extract as a separate Client Component
-
Check for the anti-pattern where a large Server Component was converted to a Client Component just to pass an event handler — suggest extracting the interactive element instead.
-
In Client Components that receive
paramsorsearchParamsprops, check that they are unwrapped withuse()from React, not accessed directly:const { slug } = use(params)✅const { slug } = params❌ (params is a Promise in Next.js 15)- Flag any Client Component that destructures params/searchParams without
use()orawait
Output format:
- List each component with its status: ✅ CORRECT, ⚠️ UNNECESSARY 'use client', or ❌ MISSING REQUIRED 'use client'
- For each issue, show the specific lines causing the classification
- Provide a concrete refactor suggestion for each problem found
- End with a summary: X components reviewed, Y issues found, estimated server-rendering improvement
If no path is provided in $ARGUMENTS, analyze all components in the current directory and subdirectories.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 36 lines · 0 tokens per session scan A 984ea75393bf
check-boundaries is a command published in the GitHub repository pruthvinathJV/nextjs-claude-code-kit (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 482 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
review
Review code changes against project conventions.
gh-debug-issue
../../.mastracode/commands/gh-debug-issue.md.
commit
../../.mastracode/commands/commit.md.
ralph-plan
../../.mastracode/commands/ralph-plan.md.
/release
Release a new version — updates CHANGELOG, pyproject.toml, creates git tag, and pushes.
manage-changes
Analyze and integrate PRD changes mid-development.